From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0E25B6453 for ; Tue, 22 Mar 2022 21:45:07 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id CDC35C340EE; Tue, 22 Mar 2022 21:45:06 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1647985506; bh=0kwVp1uCVNM1slEZwqSgpEq9T2hfQzOGDOCOgOTuyLo=; h=Date:To:From:In-Reply-To:Subject:From; b=RlALM8E+W1qsx2BH17YhyxMquSfH+KVsC+RJ3tMVNykvNYWWI827HAWsd1M9fAj9u 3gr/ePy7kV+UmVmvtjJmVXaPFXFUbnpTIcw22QbMR+BjC8Ub3UZYJyr1hA8ld0jslg tHr8hxdqVEG8XeaUS42yMGeRM5aLpLf/vE6OYbZM= Date: Tue, 22 Mar 2022 14:45:06 -0700 To: zhengqi.arch@bytedance.com,willy@infradead.org,song.bao.hua@hisilicon.com,osalvador@suse.de,mike.kravetz@oracle.com,mhocko@suse.com,fam.zheng@bytedance.com,duanxiongchun@bytedance.com,david@redhat.com,corbet@lwn.net,chenhuang5@huawei.com,bodeddub@amazon.com,songmuchun@bytedance.com,akpm@linux-foundation.org,patches@lists.linux.dev,linux-mm@kvack.org,mm-commits@vger.kernel.org,torvalds@linux-foundation.org,akpm@linux-foundation.org From: Andrew Morton In-Reply-To: <20220322143803.04a5e59a07e48284f196a2f9@linux-foundation.org> Subject: [patch 130/227] mm: sparsemem: use page table lock to protect kernel pmd operations Message-Id: <20220322214506.CDC35C340EE@smtp.kernel.org> Precedence: bulk X-Mailing-List: patches@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: From: Muchun Song Subject: mm: sparsemem: use page table lock to protect kernel pmd operations The init_mm.page_table_lock is used to protect kernel page tables, we can use it to serialize splitting vmemmap PMD mappings instead of mmap write lock, which can increase the concurrency of vmemmap_remap_free(). Actually, It increase the concurrency between allocations of HugeTLB pages. But it is not the only benefit. There are a lot of users of mmap read lock of init_mm. The mmap write lock is holding through vmemmap_remap_free(), removing mmap write lock usage to make it does not affect other users of mmap read lock. It is not making anything worse and always a win to move. Now the kernel page table walker does not hold the page_table_lock when walking pmd entries. There may be consistency issue of a pmd entry, because pmd entry might change from a huge pmd entry to a PTE page table. There is only one user of kernel page table walker, namely ptdump. The ptdump already considers the consistency, which use a local variable to cache the value of pmd entry. But we also need to update ->action to ACTION_CONTINUE to make sure the walker does not walk every pte entry again when concurrent thread has split the huge pmd. Link: https://lkml.kernel.org/r/20211101031651.75851-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Barry Song Cc: Bodeddula Balasubramaniam Cc: Chen Huang Cc: David Hildenbrand Cc: Fam Zheng Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qi Zheng Cc: Xiongchun Duan Signed-off-by: Andrew Morton --- mm/ptdump.c | 16 ++++++++++---- mm/sparse-vmemmap.c | 47 +++++++++++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 20 deletions(-) --- a/mm/ptdump.c~mm-sparsemem-use-page-table-lock-to-protect-kernel-pmd-operations +++ a/mm/ptdump.c @@ -40,8 +40,10 @@ static int ptdump_pgd_entry(pgd_t *pgd, if (st->effective_prot) st->effective_prot(st, 0, pgd_val(val)); - if (pgd_leaf(val)) + if (pgd_leaf(val)) { st->note_page(st, addr, 0, pgd_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -61,8 +63,10 @@ static int ptdump_p4d_entry(p4d_t *p4d, if (st->effective_prot) st->effective_prot(st, 1, p4d_val(val)); - if (p4d_leaf(val)) + if (p4d_leaf(val)) { st->note_page(st, addr, 1, p4d_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -82,8 +86,10 @@ static int ptdump_pud_entry(pud_t *pud, if (st->effective_prot) st->effective_prot(st, 2, pud_val(val)); - if (pud_leaf(val)) + if (pud_leaf(val)) { st->note_page(st, addr, 2, pud_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -101,8 +107,10 @@ static int ptdump_pmd_entry(pmd_t *pmd, if (st->effective_prot) st->effective_prot(st, 3, pmd_val(val)); - if (pmd_leaf(val)) + if (pmd_leaf(val)) { st->note_page(st, addr, 3, pmd_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } --- a/mm/sparse-vmemmap.c~mm-sparsemem-use-page-table-lock-to-protect-kernel-pmd-operations +++ a/mm/sparse-vmemmap.c @@ -53,8 +53,7 @@ struct vmemmap_remap_walk { struct list_head *vmemmap_pages; }; -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, - struct vmemmap_remap_walk *walk) +static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) { pmd_t __pmd; int i; @@ -76,15 +75,34 @@ static int split_vmemmap_huge_pmd(pmd_t set_pte_at(&init_mm, addr, pte, entry); } - /* Make pte visible before pmd. See comment in pmd_install(). */ - smp_wmb(); - pmd_populate_kernel(&init_mm, pmd, pgtable); - - flush_tlb_kernel_range(start, start + PMD_SIZE); + spin_lock(&init_mm.page_table_lock); + if (likely(pmd_leaf(*pmd))) { + /* Make pte visible before pmd. See comment in pmd_install(). */ + smp_wmb(); + pmd_populate_kernel(&init_mm, pmd, pgtable); + flush_tlb_kernel_range(start, start + PMD_SIZE); + } else { + pte_free_kernel(&init_mm, pgtable); + } + spin_unlock(&init_mm.page_table_lock); return 0; } +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) +{ + int leaf; + + spin_lock(&init_mm.page_table_lock); + leaf = pmd_leaf(*pmd); + spin_unlock(&init_mm.page_table_lock); + + if (!leaf) + return 0; + + return __split_vmemmap_huge_pmd(pmd, start); +} + static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct vmemmap_remap_walk *walk) @@ -121,13 +139,12 @@ static int vmemmap_pmd_range(pud_t *pud, pmd = pmd_offset(pud, addr); do { - if (pmd_leaf(*pmd)) { - int ret; + int ret; + + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK); + if (ret) + return ret; - ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk); - if (ret) - return ret; - } next = pmd_addr_end(addr, end); vmemmap_pte_range(pmd, addr, next, walk); } while (pmd++, addr = next, addr != end); @@ -321,10 +338,8 @@ int vmemmap_remap_free(unsigned long sta */ BUG_ON(start - reuse != PAGE_SIZE); - mmap_write_lock(&init_mm); + mmap_read_lock(&init_mm); ret = vmemmap_remap_range(reuse, end, &walk); - mmap_write_downgrade(&init_mm); - if (ret && walk.nr_walked) { end = reuse + walk.nr_walked * PAGE_SIZE; /* _ From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id EA934C4332F for ; Tue, 22 Mar 2022 21:45:36 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230376AbiCVVrD (ORCPT ); Tue, 22 Mar 2022 17:47:03 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:59948 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S236369AbiCVVqo (ORCPT ); Tue, 22 Mar 2022 17:46:44 -0400 Received: from dfw.source.kernel.org (dfw.source.kernel.org [IPv6:2604:1380:4641:c500::1]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DDE775F8E8 for ; Tue, 22 Mar 2022 14:45:07 -0700 (PDT) Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dfw.source.kernel.org (Postfix) with ESMTPS id 7B09C6104C for ; Tue, 22 Mar 2022 21:45:07 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id CDC35C340EE; Tue, 22 Mar 2022 21:45:06 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1647985506; bh=0kwVp1uCVNM1slEZwqSgpEq9T2hfQzOGDOCOgOTuyLo=; h=Date:To:From:In-Reply-To:Subject:From; b=RlALM8E+W1qsx2BH17YhyxMquSfH+KVsC+RJ3tMVNykvNYWWI827HAWsd1M9fAj9u 3gr/ePy7kV+UmVmvtjJmVXaPFXFUbnpTIcw22QbMR+BjC8Ub3UZYJyr1hA8ld0jslg tHr8hxdqVEG8XeaUS42yMGeRM5aLpLf/vE6OYbZM= Date: Tue, 22 Mar 2022 14:45:06 -0700 To: zhengqi.arch@bytedance.com, willy@infradead.org, song.bao.hua@hisilicon.com, osalvador@suse.de, mike.kravetz@oracle.com, mhocko@suse.com, fam.zheng@bytedance.com, duanxiongchun@bytedance.com, david@redhat.com, corbet@lwn.net, chenhuang5@huawei.com, bodeddub@amazon.com, songmuchun@bytedance.com, akpm@linux-foundation.org, patches@lists.linux.dev, linux-mm@kvack.org, mm-commits@vger.kernel.org, torvalds@linux-foundation.org, akpm@linux-foundation.org From: Andrew Morton In-Reply-To: <20220322143803.04a5e59a07e48284f196a2f9@linux-foundation.org> Subject: [patch 130/227] mm: sparsemem: use page table lock to protect kernel pmd operations Message-Id: <20220322214506.CDC35C340EE@smtp.kernel.org> Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org From: Muchun Song Subject: mm: sparsemem: use page table lock to protect kernel pmd operations The init_mm.page_table_lock is used to protect kernel page tables, we can use it to serialize splitting vmemmap PMD mappings instead of mmap write lock, which can increase the concurrency of vmemmap_remap_free(). Actually, It increase the concurrency between allocations of HugeTLB pages. But it is not the only benefit. There are a lot of users of mmap read lock of init_mm. The mmap write lock is holding through vmemmap_remap_free(), removing mmap write lock usage to make it does not affect other users of mmap read lock. It is not making anything worse and always a win to move. Now the kernel page table walker does not hold the page_table_lock when walking pmd entries. There may be consistency issue of a pmd entry, because pmd entry might change from a huge pmd entry to a PTE page table. There is only one user of kernel page table walker, namely ptdump. The ptdump already considers the consistency, which use a local variable to cache the value of pmd entry. But we also need to update ->action to ACTION_CONTINUE to make sure the walker does not walk every pte entry again when concurrent thread has split the huge pmd. Link: https://lkml.kernel.org/r/20211101031651.75851-4-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Barry Song Cc: Bodeddula Balasubramaniam Cc: Chen Huang Cc: David Hildenbrand Cc: Fam Zheng Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: Mike Kravetz Cc: Oscar Salvador Cc: Qi Zheng Cc: Xiongchun Duan Signed-off-by: Andrew Morton --- mm/ptdump.c | 16 ++++++++++---- mm/sparse-vmemmap.c | 47 +++++++++++++++++++++++++++--------------- 2 files changed, 43 insertions(+), 20 deletions(-) --- a/mm/ptdump.c~mm-sparsemem-use-page-table-lock-to-protect-kernel-pmd-operations +++ a/mm/ptdump.c @@ -40,8 +40,10 @@ static int ptdump_pgd_entry(pgd_t *pgd, if (st->effective_prot) st->effective_prot(st, 0, pgd_val(val)); - if (pgd_leaf(val)) + if (pgd_leaf(val)) { st->note_page(st, addr, 0, pgd_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -61,8 +63,10 @@ static int ptdump_p4d_entry(p4d_t *p4d, if (st->effective_prot) st->effective_prot(st, 1, p4d_val(val)); - if (p4d_leaf(val)) + if (p4d_leaf(val)) { st->note_page(st, addr, 1, p4d_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -82,8 +86,10 @@ static int ptdump_pud_entry(pud_t *pud, if (st->effective_prot) st->effective_prot(st, 2, pud_val(val)); - if (pud_leaf(val)) + if (pud_leaf(val)) { st->note_page(st, addr, 2, pud_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } @@ -101,8 +107,10 @@ static int ptdump_pmd_entry(pmd_t *pmd, if (st->effective_prot) st->effective_prot(st, 3, pmd_val(val)); - if (pmd_leaf(val)) + if (pmd_leaf(val)) { st->note_page(st, addr, 3, pmd_val(val)); + walk->action = ACTION_CONTINUE; + } return 0; } --- a/mm/sparse-vmemmap.c~mm-sparsemem-use-page-table-lock-to-protect-kernel-pmd-operations +++ a/mm/sparse-vmemmap.c @@ -53,8 +53,7 @@ struct vmemmap_remap_walk { struct list_head *vmemmap_pages; }; -static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start, - struct vmemmap_remap_walk *walk) +static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) { pmd_t __pmd; int i; @@ -76,15 +75,34 @@ static int split_vmemmap_huge_pmd(pmd_t set_pte_at(&init_mm, addr, pte, entry); } - /* Make pte visible before pmd. See comment in pmd_install(). */ - smp_wmb(); - pmd_populate_kernel(&init_mm, pmd, pgtable); - - flush_tlb_kernel_range(start, start + PMD_SIZE); + spin_lock(&init_mm.page_table_lock); + if (likely(pmd_leaf(*pmd))) { + /* Make pte visible before pmd. See comment in pmd_install(). */ + smp_wmb(); + pmd_populate_kernel(&init_mm, pmd, pgtable); + flush_tlb_kernel_range(start, start + PMD_SIZE); + } else { + pte_free_kernel(&init_mm, pgtable); + } + spin_unlock(&init_mm.page_table_lock); return 0; } +static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start) +{ + int leaf; + + spin_lock(&init_mm.page_table_lock); + leaf = pmd_leaf(*pmd); + spin_unlock(&init_mm.page_table_lock); + + if (!leaf) + return 0; + + return __split_vmemmap_huge_pmd(pmd, start); +} + static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct vmemmap_remap_walk *walk) @@ -121,13 +139,12 @@ static int vmemmap_pmd_range(pud_t *pud, pmd = pmd_offset(pud, addr); do { - if (pmd_leaf(*pmd)) { - int ret; + int ret; + + ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK); + if (ret) + return ret; - ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK, walk); - if (ret) - return ret; - } next = pmd_addr_end(addr, end); vmemmap_pte_range(pmd, addr, next, walk); } while (pmd++, addr = next, addr != end); @@ -321,10 +338,8 @@ int vmemmap_remap_free(unsigned long sta */ BUG_ON(start - reuse != PAGE_SIZE); - mmap_write_lock(&init_mm); + mmap_read_lock(&init_mm); ret = vmemmap_remap_range(reuse, end, &walk); - mmap_write_downgrade(&init_mm); - if (ret && walk.nr_walked) { end = reuse + walk.nr_walked * PAGE_SIZE; /* _